SAMPart3D: Segment Any Part in 3D Objects

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Yunhan, Huang, Yukun, Guo, Yuan-Chen, Lu, Liangjun, Wu, Xiaoyang, Lam, Edmund Y., Cao, Yan-Pei, Liu, Xihui
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915022799634432
author Yang, Yunhan
Huang, Yukun
Guo, Yuan-Chen
Lu, Liangjun
Wu, Xiaoyang
Lam, Edmund Y.
Cao, Yan-Pei
Liu, Xihui
author_facet Yang, Yunhan
Huang, Yukun
Guo, Yuan-Chen
Lu, Liangjun
Wu, Xiaoyang
Lam, Edmund Y.
Cao, Yan-Pei
Liu, Xihui
contents 3D part segmentation is a crucial and challenging task in 3D perception, playing a vital role in applications such as robotics, 3D generation, and 3D editing. Recent methods harness the powerful Vision Language Models (VLMs) for 2D-to-3D knowledge distillation, achieving zero-shot 3D part segmentation. However, these methods are limited by their reliance on text prompts, which restricts the scalability to large-scale unlabeled datasets and the flexibility in handling part ambiguities. In this work, we introduce SAMPart3D, a scalable zero-shot 3D part segmentation framework that segments any 3D object into semantic parts at multiple granularities, without requiring predefined part label sets as text prompts. For scalability, we use text-agnostic vision foundation models to distill a 3D feature extraction backbone, allowing scaling to large unlabeled 3D datasets to learn rich 3D priors. For flexibility, we distill scale-conditioned part-aware 3D features for 3D part segmentation at multiple granularities. Once the segmented parts are obtained from the scale-conditioned part-aware 3D features, we use VLMs to assign semantic labels to each part based on the multi-view renderings. Compared to previous methods, our SAMPart3D can scale to the recent large-scale 3D object dataset Objaverse and handle complex, non-ordinary objects. Additionally, we contribute a new 3D part segmentation benchmark to address the lack of diversity and complexity of objects and parts in existing benchmarks. Experiments show that our SAMPart3D significantly outperforms existing zero-shot 3D part segmentation methods, and can facilitate various applications such as part-level editing and interactive segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2411_07184
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SAMPart3D: Segment Any Part in 3D Objects
Yang, Yunhan
Huang, Yukun
Guo, Yuan-Chen
Lu, Liangjun
Wu, Xiaoyang
Lam, Edmund Y.
Cao, Yan-Pei
Liu, Xihui
Computer Vision and Pattern Recognition
3D part segmentation is a crucial and challenging task in 3D perception, playing a vital role in applications such as robotics, 3D generation, and 3D editing. Recent methods harness the powerful Vision Language Models (VLMs) for 2D-to-3D knowledge distillation, achieving zero-shot 3D part segmentation. However, these methods are limited by their reliance on text prompts, which restricts the scalability to large-scale unlabeled datasets and the flexibility in handling part ambiguities. In this work, we introduce SAMPart3D, a scalable zero-shot 3D part segmentation framework that segments any 3D object into semantic parts at multiple granularities, without requiring predefined part label sets as text prompts. For scalability, we use text-agnostic vision foundation models to distill a 3D feature extraction backbone, allowing scaling to large unlabeled 3D datasets to learn rich 3D priors. For flexibility, we distill scale-conditioned part-aware 3D features for 3D part segmentation at multiple granularities. Once the segmented parts are obtained from the scale-conditioned part-aware 3D features, we use VLMs to assign semantic labels to each part based on the multi-view renderings. Compared to previous methods, our SAMPart3D can scale to the recent large-scale 3D object dataset Objaverse and handle complex, non-ordinary objects. Additionally, we contribute a new 3D part segmentation benchmark to address the lack of diversity and complexity of objects and parts in existing benchmarks. Experiments show that our SAMPart3D significantly outperforms existing zero-shot 3D part segmentation methods, and can facilitate various applications such as part-level editing and interactive segmentation.
title SAMPart3D: Segment Any Part in 3D Objects
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.07184